AI Research News Feeds for September 9th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• Flow-based generative models as iterative algorithms in probability space
• The feasibility of multi-graph alignment: a Bayesian approach
• Randomized Quasi-Monte Carlo Features for Kernel Approximation
• The Ground Cost for Optimal Transport of Angular Velocity
• Efficient $Q$-Learning and Actor-Critic Methods for Robust Average Reward Reinforcement Learning
• Precise Bayesian Neural Networks
• GenAI-Powered Inference
• Beyond ATE: Multi-Criteria Design for A/B Testing
• Predicting Market Troughs: A Machine Learning Approach with Causal Interpretation
• On Rate-Optimal Partitioning Classification from Observable and from Privatised Data
• Variational Inference for Uncertainty Quantification: an Analysis of Trade-offs
• Robust Generative Learning with Lipschitz-Regularized $\alpha$-Divergences Allows Minimal Assumptions on Target Distributions
• Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary Distribution
• Autoencoders in Function Space
• Confirmation Bias in Gaussian Mixture Models
• Limit Theorems for Stochastic Gradient Descent with Infinite Variance
• Sequential Controlled Langevin Diffusions
• Error-quantified Conformal Inference for Time Series
• Uncertainty quantification for Markov chain induced martingales with application to temporal difference learning
• KD$^{2}$M: A unifying framework for feature knowledge distillation
• Quantum-inspired probability metrics define a complete, universal space for statistical learning
• Catapult Dynamics and Phase Transitions in Quadratic Nets
• Sequential Gibbs Posteriors with Applications to Principal Component Analysis
• Probabilistic Shapley Value Modeling and Inference
• The Over-Certainty Phenomenon in Modern Test-Time Adaptation Algorithms
• Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer
• Optimality of Approximate Message Passing Algorithms for Spiked Matrix Models with Rotationally Invariant Noise
• A Fully Parameter-Free Second-Order Algorithm for Convex-Concave Minimax Problems
• Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures
• Achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models
• A Theoretical Justification for Asymmetric Actor-Critic Algorithms
• Statistical description and dimension reduction of categorical trajectories with multivariate functional principal components
• Stereovision Image Processing for Planetary Navigation Maps with Semi-Global Matching and Superpixel Segmentation
• Brain Tumor Detection Through Diverse CNN Architectures in IoT Healthcare Industries: Fast R-CNN, U-Net, Transfer Learning-Based CNN, and Fully Connected CNN
• eKalibr-Inertial: Continuous-Time Spatiotemporal Calibration for Event-Based Visual-Inertial Systems
• O$^3$Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation
• Contrastive Anatomy-Contrast Disentanglement: A Domain-General MRI Harmonization Method
• From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans
• Towards In-Air Ultrasonic QR Codes: Deep Learning for Classification of Passive Reflector Constellations
• MM-DINOv2: Adapting Foundation Models for Multi-Modal Medical Image Analysis
• LLaDA-VLA: Vision Language Diffusion Action Models
• Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data
• F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions
• Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments
• Can Machines Imitate Humans? Integrative Turing-like tests for Language and Vision Demonstrate a Narrowing Gap
• ADIR: Adaptive Diffusion for Image Reconstruction
• The GOOSE Dataset for Perception in Unstructured Environments
• EdgeSAM: Prompt-In-the-Loop Distillation for SAM
• LD-SDM: Language-Driven Hierarchical Species Distribution Modeling
• Osprey: Pixel Understanding with Visual Instruction Tuning
• Sequential Least-Squares Estimators with Fast Randomized Sketching for Linear Statistical Models
• Learning from one graph: transductive learning guarantees via the geometry of small random worlds
• Interpretable dimension reduction for compositional data
• Event Spectroscopy: Event-based Multispectral and Depth Sensing using Structured Light
• Pothole Detection and Recognition based on Transfer Learning
• Raw2Event: Converting Raw Frame Camera into Event Camera
• D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning
• UrbanTwin: High-Fidelity Synthetic Replicas of Roadside Lidar Datasets
• P3-SAM: Native 3D Part Segmentation
• SynthDrive: Scalable Real2Sim2Real Sensor Simulation Pipeline for High-Fidelity Asset Generation and Driving Data Synthesis
• MIORe & VAR-MIORe: Benchmarks to Push the Boundaries of Restoration
• UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward
• Video-Based MPAA Rating Prediction: An Attention-Driven Hybrid Architecture Using Contrastive Learning
• Curia: A Multi-Modal Foundation Model for Radiology
• Leveraging Generic Foundation Models for Multimodal Surgical Data Analysis
• Evaluating the Impact of Adversarial Attacks on Traffic Sign Classification using the LISA Dataset
• ToonOut: Fine-tuned Background-Removal for Anime Characters
• Automated Radiographic Total Sharp Score (ARTSS) in Rheumatoid Arthritis: A Solution to Reduce Inter-Intra Reader Variation and Enhancing Clinical Practice
• Matching Shapes Under Different Topologies: A Topology-Adaptive Deformation Guided Approach
• A New Hybrid Model of Generative Adversarial Network and You Only Look Once Algorithm for Automatic License-Plate Recognition
• Barlow-Swin: Toward a novel siamese-based segmentation architecture using Swin-Transformers
• Intraoperative 2D/3D Registration via Spherical Similarity Learning and Inference-Time Differentiable Levenberg-Marquardt Optimization
• BIR-Adapter: A Low-Complexity Diffusion Model Adapter for Blind Image Restoration
• FoMo4Wheat: Toward reliable crop vision foundation models with globally curated data
• H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers
• Layer-Wise Anomaly Detection in Directed Energy Deposition using High-Fidelity Fringe Projection Profilometry
• A Synthetic-to-Real Dehazing Method based on Domain Unification
• Phantom-Insight: Adaptive Multi-cue Fusion for Video Camouflaged Object Detection with Multimodal LLM
• When Language Model Guides Vision: Grounding DINO for Cattle Muzzle Detection
• Perception-oriented Bidirectional Attention Network for Image Super-resolution Quality Assessment
• Cross3DReg: Towards a Large-scale Real-world Cross-source Point Cloud Registration Benchmark
• A Statistical 3D Stomach Shape Model for Anatomical Analysis
• Does DINOv3 Set a New Medical Vision Standard?
• FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection
• WS$^2$: Weakly Supervised Segmentation using Before-After Supervision in Waste Sorting
• TIDE: Achieving Balanced Subject-Driven Image Generation via Target-Instructed Diffusion Enhancement
• Predicting Brain Tumor Response to Therapy using a Hybrid Deep Learning and Radiomics Approach
• Benchmarking EfficientTAM on FMO datasets
• Back To The Drawing Board: Rethinking Scene-Level Sketch-Based Image Retrieval
• Evolving from Unknown to Known: Retentive Angular Representation Learning for Incremental Open Set Recognition
• CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis
• Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoising
• Investigating Location-Regularised Self-Supervised Feature Learning for Seafloor Visual Imagery
• Online Clustering of Seafloor Imagery for Interpretation during Long-Term AUV Operations
• VIM-GS: Visual-Inertial Monocular Gaussian Splatting via Object-level Guidance in Large Scenes
• BioLite U-Net: Edge-Deployable Semantic Segmentation for In Situ Bioprinting Monitoring
• STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment
• Cortex-Synth: Differentiable Topology-Aware 3D Skeleton Synthesis with Hierarchical Graph Attention
• MRI-Based Brain Tumor Detection through an Explainable EfficientNetV2 and MLP-Mixer-Attention Architecture
• Zero-shot 3D-Aware Trajectory-Guided image-to-video generation via Test-Time Training
• Co-Seg: Mutual Prompt-Guided Collaborative Learning for Tissue and Nuclei Segmentation
• Analysis of Blood Report Images Using General Purpose Vision-Language Models
• Multi-Stage Graph Neural Networks for Data-Driven Prediction of Natural Convection in Enclosed Cavities
• Home-made Diffusion Model from Scratch to Hatch
• High-Quality Tomographic Image Reconstruction Integrating Neural Networks and Mathematical Optimization
• MedSeqFT: Sequential Fine-tuning Foundation Models for 3D Medical Image Segmentation
• PathoHR: Hierarchical Reasoning for Vision-Language Models in Pathology
• CARDIE: clustering algorithm on relevant descriptors for image enhancement
• RetinaGuard: Obfuscating Retinal Age in Fundus Images for Biometric Privacy Preserving
• UniVerse-1: Unified Audio-Video Generation via Stitching of Experts
• AI-Based Applied Innovation for Fracture Detection in X-rays Using Custom CNN and Transfer Learning Models
• Exploring Light-Weight Object Recognition for Real-Time Document Detection
• Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes
• AI-driven Remote Facial Skin Hydration and TEWL Assessment from Selfie Images: A Systematic Solution
• Prototype-Aware Multimodal Alignment for Open-Vocabulary Visual Grounding
• Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learning
• Text4Seg++: Advancing Image Segmentation via Generative Language Modeling
• Towards scalable organ level 3D plant segmentation: Bridging the data algorithm computing gap
• Quantitative Currency Evaluation in Low-Resource Settings through Pattern Analysis to Assist Visually Impaired Users
• Multi-Modal Camera-Based Detection of Vulnerable Road Users
• Harnessing Object Grounding for Time-Sensitive Video Understanding
• Your Super Resolution Model is not Enough for Tackling Real-World Scenarios
• AI-based response assessment and prediction in longitudinal imaging for brain metastases treated with stereotactic radiosurgery
• 3DOF+Quantization: 3DGS quantization for large scenes with limited Degrees of Freedom
• JRN-Geo: A Joint Perception Network based on RGB and Normal images for Cross-view Geo-localization
• Multi-LVI-SAM: A Robust LiDAR-Visual-Inertial Odometry for Multiple Fisheye Cameras
• Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulation
• PictOBI-20k: Unveiling Large Multimodal Models in Visual Decipherment for Pictographic Oracle Bone Characters
• Posterior shape models revisited: Improving 3D reconstructions from partial data using target specific models
• 3DPillars: Pillar-based two-stage 3D object detection
• CRAB: Camera-Radar Fusion for Reducing Depth Ambiguity in Backward Projection based View Transformation
• A Probabilistic Segment Anything Model for Ambiguity-Aware Medical Image Segmentation
• BTCChat: Advancing Remote Sensing Bi-temporal Change Captioning with Multimodal Large Language Model
• A Fine-Grained Attention and Geometric Correspondence Model for Musculoskeletal Risk Classification in Athletes Using Multimodal Visual and Skeletal Features
• Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models
• AttriPrompt: Dynamic Prompt Composition Learning for CLIP
• Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching
• Dual Interaction Network with Cross-Image Attention for Medical Image Segmentation
• StripDet: Strip Attention-Based Lightweight 3D Object Detection from Point Cloud
• Neural Bloom: A Deep Learning Approach to Real-Time Lighting
• Spatial-Aware Self-Supervision for Medical 3D Imaging with Multi-Granularity Observable Tasks
• OmniStyle2: Scalable and High Quality Artistic Style Transfer Data Generation via Destylization
• Multi-Strategy Guided Diffusion via Sparse Masking Temporal Reweighting Distribution Correction
• Motion Aware ViT-based Framework for Monocular 6-DoF Spacecraft Pose Estimation
• BLaVe-CoT: Consistency-Aware Visual Question Answering for Blind and Low Vision Users
• Cross-Modal Enhancement and Benchmark for UAV-based Open-Vocabulary Object Detection
• Micro-Expression Recognition via Fine-Grained Dynamic Perception
• DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-temporal Fusion
• Context-Aware Knowledge Distillation with Adaptive Weighting for Image Classification
• A Real-Time, Vision-Based System for Badminton Smash Speed Estimation on Mobile Devices
• A Stroke-Level Large-Scale Database of Chinese Character Handwriting and the OpenHandWrite_Toolbox for Handwriting Research
• Anticipatory Fall Detection in Humans with Hybrid Directed Graph Neural Networks and Long Short-Term Memory
• Systematic Integration of Attention Modules into CNNs for Accurate and Generalizable Medical Image Diagnosis
• Vision-Based Object Detection for UAV Solar Panel Inspection Using an Enhanced Defects Dataset
• Dynamic Sensitivity Filter Pruning using Multi-Agent Reinforcement Learning For DCNN's
• Veriserum: A dual-plane fluoroscopic dataset with knee implant phantoms for deep learning in medical imaging
• Quaternion Approximation Networks for Enhanced Image Classification and Oriented Object Detection
• Visibility-Aware Language Aggregation for Open-Vocabulary Segmentation in 3D Gaussian Splatting
• DuoCLR: Dual-Surrogate Contrastive Learning for Skeleton-based Human Action Segmentation
• RED: Robust Event-Guided Motion Deblurring with Modality-Specific Disentangled Representation
• Sensitivity-Aware Post-Training Quantization for Deep Neural Networks
• Reconstruction and Reenactment Separated Method for Realistic Gaussian Head
• MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios
• Patch-level Kernel Alignment for Self-Supervised Dense Representation Learning
• SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models
• Evaluating YOLO Architectures: Implications for Real-Time Vehicle Detection in Urban Environments of Bangladesh
• EditIDv2: Editable ID Customization with Data-Lubricated ID Feature Integration for Text-to-Image Generation
• OOTSM: A Decoupled Linguistic Framework for Effective Scene Graph Anticipation
• WIPUNet: A Physics-inspired Network with Weighted Inductive Biases for Image Denoising
• Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance
• MeshMetrics: A Precise Implementation of Distance-Based Image Segmentation Metrics
• Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization
• SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards
• Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework
• Label Smoothing++: Enhanced Label Regularization for Training Neural Networks
• BeSimulator: A Large Language Model Powered Text-based Behavior Simulator
• Causal Representation Learning with Generative Artificial Intelligence: Application to Texts as Treatments
• ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries
• ElectroVizQA: How well do Multi-modal LLMs perform in Electronics Visual Question Answering?
• ChinaTravel: An Open-Ended Benchmark for Language Agents in Chinese Travel Planning
• AI Sees Your Location, But With A Bias Toward The Wealthy World
• VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
• MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs
• OpenDeception: Benchmarking and Investigating AI Deceptive Behaviors via Open-ended Interaction Simulation
• A Minimum Description Length Approach to Regularization in Neural Networks
• InterFeat: A Pipeline for Finding Interesting Scientific Features
• Project Riley: Multimodal Multi-Agent LLM Collaboration with Emotional Reasoning and Voting
• TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review
• Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Models
• RADIANT: Retrieval AugmenteD entIty-context AligNmenT -- Introducing RAG-ability and Entity-Context Divergence
• Dynamic Injection of Entity Knowledge into Dense Retrievers
• Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models
• The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors
• MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning
• ResearchArena: Benchmarking Large Language Models' Ability to Collect and Organize Information as Research Agents
• Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework
• Through the Prism of Culture: Evaluating LLMs' Understanding of Indian Subcultures and Traditions
• Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs
• Position: LLMs Can be Good Tutors in English Education
• Reinforced Lifelong Editing for Language Models
• Improve LLM-as-a-Judge Ability as a General Ability
• Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models
• Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations
• PlainQAFact: Retrieval-augmented Factual Consistency Evaluation Metric for Biomedical Plain Language Summarization
• LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL
• Learning to Reason for Long-Form Story Generation
• Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
• Advancing Scientific Text Classification: Fine-Tuned Models with Dataset Expansion and Hard-Voting
• Assessing and Mitigating Medical Knowledge Drift and Conflicts in Large Language Models
• Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis
• Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes
• VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models
• Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs
• Fast Quiet-STaR: Thinking Without Thought Tokens
• Rhapsody: A Dataset for Highlight Detection in Podcasts
• Self-Critique and Refinement for Faithful Natural Language Explanations
• ChatCFD: An LLM-Driven Agent for End-to-End CFD Automation with Domain-Specific Structured Reasoning
• Interleaving Reasoning for Better Text-to-Image Generation
• Multiple Noises in Diffusion Model for Semi-Supervised Multi-Domain Translation
• Support or Refute: Analyzing the Stance of Evidence to Detect Out-of-Context Mis- and Disinformation
• Grammaticality illusion or ambiguous interpretation? Event-related potentials reveal the nature of the missing-NP effect in Mandarin centre-embedded structures
• Repetition Improves Language Model Embeddings
• Linearly Controlled Language Generation with Performative Guarantees
• Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text
• A Principled Framework for Evaluating on Typologically Diverse Languages
• Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective
• Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning
• Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models
• Conversational Code Generation: a Case Study of Designing a Dialogue System for Generating Driving Scenarios for Testing Autonomous Vehicles
• GASE: Generatively Augmented Sentence Encoding
• Exploring the Limits of Large Language Models: A Systematic Evaluation of Masked Text Processing Ability through MskQA and MskCal
• HierTOD: A Task-Oriented Dialogue System Driven by Hierarchical Goals
• Lessons from Studying Two-Hop Latent Reasoning
• Think-to-Talk or Talk-to-Think? When LLMs Come Up with an Answer in Multi-Hop Arithmetic Reasoning
• Concept Bottleneck Large Language Models
• Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise
• Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detection
• Knowledge Editing through Chain-of-Thought
• OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
• LAMDAS: LLM as an Implicit Classifier for Domain-specific Data Selection
• SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion
• HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models
• Guided Decoding and Its Critical Role in Retrieval-Augmented Generation
• Modelling Intertextuality with N-gram Embeddings
• Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval
• IntrEx: A Dataset for Modeling Engagement in Educational Conversations
• ParCzech4Speech: A New Speech Corpus Derived from Czech Parliamentary Data
• Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments
• Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint
• MachineLearningLM: Continued Pretraining Language Models on Millions of Synthetic Tabular Prediction Tasks Scales In-Context ML
• MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security
• Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem
• A Comparative Benchmark of Large Language Models for Labelling Wind Turbine Maintenance Logs
• COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens
• EPT Benchmark: Evaluation of Persian Trustworthiness in Large Language Models
• The Majority is not always right: RL training for solution aggregation
• UNH at CheckThat! 2025: Fine-tuning Vs Prompting in Claim Extraction
• mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
• Proof-Carrying Numbers (PCN): A Protocol for Trustworthy Numeric Answers from LLMs via Claim Verification
• Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
• Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
• On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts
• On the Contribution of Lexical Features to Speech Emotion Recognition
• An Ethically Grounded LLM-Based Approach to Insider Threat Synthesis and Detection
• From Staff Messages to Actionable Insights: A Multi-Stage LLM Classification Framework for Healthcare Analytics
• Ad hoc conventions generalize to new referents
• Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation
• Beyond Keywords: Driving Generative Search Engine Optimization with Content-Centric Agents
• Few-Shot Query Intent Detection via Relation-Aware Prompt Learning
• Cross-Question Method Reuse in Large Language Models: From Word-Level Prediction to Rational Logical-Layer Reasoning
• Exploring Subjective Tasks in Farsi: A Survey Analysis and Evaluation of Language Models
• QCSE: A Pretrained Quantum Context-Sensitive Word Embedding for Natural Language Processing
• Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification
• LatinX: Aligning a Multilingual TTS Model with Direct Preference Optimization
• MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries
• Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modeling
• Accelerating Large Language Model Inference via Early-Exiting Algorithms
• KatotohananQA: Evaluating Truthfulness of Large Language Models in Filipino
• Multimodal Fine-grained Context Interaction Graph Modeling for Conversational Speech Synthesis
• Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge
• Orthogonal Low-rank Adaptation in Lie Groups for Continual Learning of Large Language Models
• Understanding the Influence of Synthetic Data for Text Embedders
• Augmented Fine-Tuned LLMs for Enhanced Recruitment Automation
• MSLEF: Multi-Segment LLM Ensemble Finetuning in Recruitment
• No Encore: Unlearning as Opt-Out in Music Generation
• Do LLMs exhibit the same commonsense capabilities across languages?
• WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents
• Crown, Frame, Reverse: Layer-Wise Scaling Variants for LLM Pre-Training
• Detection of trade in products derived from threatened species using machine learning and a smartphone
• Integrating Spatial and Semantic Embeddings for Stereo Sound Event Localization in Videos
• Improved Classification of Nitrogen Stress Severity in Plants Under Combined Stress Conditions Using Spatio-Temporal Deep Learning Framework
• Neural ARFIMA model for forecasting BRIC exchange rates with long memory under oil shocks and policy uncertainties
• When Secure Isn't: Assessing the Security of Machine Learning Model Sharing
• Automating API Documentation with LLMs: A BERTopic Approach
• Risk-averse Fair Multi-class Classification
• Causal Clustering for Conditional Average Treatment Effects Estimation and Subgroup Discovery
• Vector-based loss functions for turbulent flow field inpainting
• Fisher Random Walk: Automatic Debiasing Contextual Preference Inference for Large Language Model Evaluation
• Near Real-Time Dust Aerosol Detection with 3D Convolutional Neural Networks on MODIS Data
• Machine learning magnetism from simple global descriptors
• ALPHA: LLM-Enabled Active Learning for Human-Free Network Anomaly Detection
• Using Reinforcement Learning to Optimize the Global and Local Crossing Number
• Robust Analysis for Resilient AI System
• Learning in ImaginationLand: Omnidirectional Policies through 3D Generative Models (OP-Gen)
• Repeating vs. Non-Repeating FRBs: A Deep Learning Approach To Morphological Characterization
• FineServe: Precision-Aware KV Slab and Two-Level Scheduling for Heterogeneous Precision LLM Serving
• PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization
• An Explainable Framework for Particle Swarm Optimization using Landscape Analysis and Machine Learning
• MOSAIC: Minimax-Optimal Sparsity-Adaptive Inference for Change Points in Dynamic Networks
• Enhancing Low-Altitude Airspace Security: MLLM-Enabled UAV Intent Recognition
• Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift
• A Multi-Modal Deep Learning Framework for Colorectal Pathology Diagnosis: Integrating Histological and Colonoscopy Data in a Pilot Study
• IGAff: Benchmarking Adversarial Iterative and Genetic Affine Algorithms on Deep Neural Networks
• On the Reproducibility of "FairCLIP: Harnessing Fairness in Vision-Language Learning''
• Concolic Testing on Individual Fairness of Neural Network Models
• From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
• Outcome-based Exploration for LLM Reasoning
• Predicting Brain Morphogenesis via Physics-Transfer Learning
• Privacy-Preserving Offloading for Large Language Models in 6G Vehicular Networks
• Application of discrete Ricci curvature in pruning randomly wired neural networks: A case study with chest x-ray classification of COVID-19
• Handling imbalance and few-sample size in ML based Onion disease classification
• Ensembling Membership Inference Attacks Against Tabular Generative Models
• Beyond ROUGE: N-Gram Subspace Features for LLM Hallucination Detection
• RoboBallet: Planning for Multi-Robot Reaching with Graph Neural Networks and Reinforcement Learning
• Distributed Link Sparsification for Scalable Scheduling Using Graph Neural Networks (Journal Version)
• Biomedical Literature Q&A System Using Retrieval-Augmented Generation (RAG)
• New Insights into Optimal Alignment of Acoustic and Linguistic Representations for Knowledge Transfer in ASR
• Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternatives
• Robust variational neural posterior estimation for simulation-based inference
• NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables
• QualityFM: a Multimodal Physiological Signal Foundation Model with Self-Distillation for Signal Quality Challenges in Critically Ill Patients
• Lane Change Intention Prediction of two distinct Populations using a Transformer
• Contrastive Self-Supervised Network Intrusion Detection using Augmented Negative Pairs
• AI for Scientific Discovery is a Social Problem
• A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models
• BEAM: Brainwave Empathy Assessment Model for Early Childhood
• Knowledge-Guided Machine Learning for Stabilizing Near-Shortest Path Routing
• Group Effect Enhanced Generative Adversarial Imitation Learning for Individual Travel Behavior Modeling under Incentives
• Barycentric Neural Networks and Length-Weighted Persistent Entropy Loss: A Green Geometric and Topological Framework for Function Approximation
• Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks
• RT-HCP: Dealing with Inference Delays and Sample Efficiency to Learn Directly on Robotic Platforms
• Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization
• Asynchronous Message Passing for Addressing Oversquashing in Graph Neural Networks
• Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning
• \texttt{R$^\textbf{2}$AI}: Towards Resistant and Resilient AI in an Evolving World
• floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL
• Performance of Conformal Prediction in Capturing Aleatoric Uncertainty
• Finetuning LLMs for Human Behavior Prediction in Social Science Experiments
• SPINN: An Optimal Self-Supervised Physics-Informed Neural Network Framework
• X-SQL: Expert Schema Linking and Understanding of Text-to-SQL with Multi-LLMs
• A novel biomass fluidized bed gasification model coupled with machine learning and CFD simulation
• A Surrogate model for High Temperature Superconducting Magnets to Predict Current Distribution with Neural Network
• If generative AI is the answer, what is the question?
• Metric Embedding Initialization-Based Differentially Private and Explainable Graph Clustering
• MCIGLE: Multimodal Exemplar-Free Class-Incremental Graph Learning
• IPR: Intelligent Prompt Routing with User-Controlled Quality-Cost Trade-offs
• RecMind: LLM-Enhanced Graph Neural Networks for Personalized Consumer Recommendations
• A Spatio-Temporal Graph Neural Networks Approach for Predicting Silent Data Corruption inducing Circuit-Level Faults
• LoaQ: Layer-wise Output Approximation Quantization
• WindFM: An Open-Source Foundation Model for Zero-Shot Wind Power Forecasting
• Text-Trained LLMs Can Zero-Shot Extrapolate PDE Dynamics
• Breaking SafetyCore: Exploring the Risks of On-Device AI Deployment
• Graph Neural Networks for Resource Allocation in Interference-limited Multi-Channel Wireless Networks with QoS Constraints
• Ban&Pick: Achieving Free Performance Gains and Inference Speedup via Smarter Routing in MoE-LLMs
• Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
• MeanFlow-Accelerated Multimodal Video-to-Audio Synthesis via One-Step Generation
• Explained, yet misunderstood: How AI Literacy shapes HR Managers' interpretation of User Interfaces in Recruiting Recommender Systems
• Safeguarding Graph Neural Networks against Topology Inference Attacks
• STL-based Optimization of Biomolecular Neural Networks for Regression and Control
• DreamPRM-1.5: Unlocking the Potential of Each Instance for Multimodal Process Reward Model Training
• Reinforcement Learning with Anticipation: A Hierarchical Approach for Long-Horizon Tasks
• Distributed Deep Learning using Stochastic Gradient Staleness
• Morphological Perceptron with Competitive Layer: Training Using Convex-Concave Procedure
• DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation
• DreamAudio: Customized Text-to-Audio Generation with Diffusion Models
• BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models
• Empirical Study of Code Large Language Models for Binary Security Patch Detection
• PolicyEvolve: Evolving Programmatic Policies by LLMs for multi-player games via Population-Based Training
• Software Dependencies 2.0: An Empirical Study of Reuse and Integration of Pre-Trained Models in Open-Source Projects
• Language Native Lightly Structured Databases for Large Language Model Driven Composite Materials Research
• Teaching Precommitted Agents: Model-Free Policy Evaluation and Control in Quasi-Hyperbolic Discounted MDPs
• SpecSwin3D: Generating Hyperspectral Imagery from Multispectral Data via Transformer Networks
• Tracking daily paths in home contexts with RSSI fingerprinting based on UWB through deep learning models
• Benchmarking Gender and Political Bias in Large Language Models
• AI Governance in Higher Education: A course design exploring regulatory, ethical and practical considerations
• Toward a Metrology for Artificial Intelligence: Hidden-Rule Environments and Reinforcement Learning
• Beamforming-LLM: What, Where and When Did I Miss?
• Statistical Inference for Misspecified Contextual Bandits
• AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs
• A Fragile Number Sense: Probing the Elemental Limits of Numerical Reasoning in LLMs
• Simulation Priors for Data-Efficient Deep Learning
• InterAct: A Large-Scale Dataset of Dynamic, Expressive and Interactive Activities between Two People in Daily Scenarios
• Unleashing Hierarchical Reasoning: An LLM-Driven Framework for Training-Free Referring Video Object Segmentation
• Exploit Tool Invocation Prompt for Tool Behavior Hijacking in LLM-Based Agentic System
• time2time: Causal Intervention in Hidden States to Simulate Rare Events in Time Series Foundation Models
• Decoding Latent Attack Surfaces in LLMs: Prompt Injection via HTML in Web Summarization
• GenAI on Wall Street -- Opportunities and Risk Controls
• ZhiFangDanTai: Fine-tuning Graph-based Retrieval-Augmented Generation Model for Traditional Chinese Medicine Formula
• Learning to Construct Knowledge through Sparse Reference Selection with Reinforcement Learning
• Uncertainty Quantification in Probabilistic Machine Learning Models: Theory, Methods, and Insights
• GeoAnalystBench: A GeoAI benchmark for assessing large language models for spatial analysis workflow and code generation
• Let's Roleplay: Examining LLM Alignment in Collaborative Dialogues
• Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs
• Challenges in Deep Learning-Based Small Organ Segmentation: A Benchmarking Perspective for Medical Research with Limited Datasets
• Meta-training of diffractive meta-neural networks for super-resolution direction of arrival estimation
• ConstStyle: Robust Domain Generalization with Unified Style Transformation
• Operationalising AI Regulatory Sandboxes under the EU AI Act: The Triple Challenge of Capacity, Coordination and Attractiveness to Providers
• Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis
• Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models
• From Vision to Validation: A Theory- and Data-Driven Construction of a GCC-Specific AI Adoption Index
• MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs
• OpenEgo: A Large-Scale Multimodal Egocentric Dataset for Dexterous Manipulation
• Combining TSL and LLM to Automate REST API Testing: A Comparative Study
• Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study
• Learning to Walk in Costume: Adversarial Motion Priors for Aesthetically Constrained Humanoids
• Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation
• Cross-Service Threat Intelligence in LLM Services using Privacy-Preserving Fingerprints
• Causal Debiasing Medical Multimodal Representation Learning with Missing Modalities
• Orchestrator: Active Inference for Multi-Agent Systems in Long-Horizon Tasks
• LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding
• Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian
• GraMFedDHAR: Graph Based Multimodal Differentially Private Federated HAR
• SEASONED: Semantic-Enhanced Self-Counterfactual Explainable Detection of Adversarial Exploiter Contracts
• Authorship Without Writing: Large Language Models and the Senior Author Analogy
• Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate
• Universality of physical neural networks with multivariate nonlinearity
• Advanced Brain Tumor Segmentation Using EMCAD: Efficient Multi-scale Convolutional Attention Decoding
• Direct-Scoring NLG Evaluators Can Use Pairwise Comparisons Too
• ForensicsData: A Digital Forensics Dataset for Large Language Models
• Plantbot: Integrating Plant and Robot through LLM Modular Agent Networks
• Comparative Evaluation of Hard and Soft Clustering for Precise Brain Tumor Segmentation in MR Imaging
• Spiking Neural Networks for Continuous Control via End-to-End Model-Based Learning
• An Empirical Analysis of Discrete Unit Representations in Speech Language Modeling Pre-training
• Governing AI R&D: A Legal Framework for Constraining Dangerous AI
• AI-in-the-Loop: Privacy Preserving Real-Time Scam Detection and Conversational Scambaiting by Leveraging LLMs and Federated Learning
• Prototyping an AI-powered Tool for Energy Efficiency in New Zealand Homes
• Between a Rock and a Hard Place: Exploiting Ethical Reasoning to Jailbreak LLMs
• Privacy Preservation and Identity Tracing Prevention in AI-Driven Eye Tracking for Interactive Learning Environments
• ThreatGPT: An Agentic AI Framework for Enhancing Public Safety through Threat Modeling
• User Privacy and Large Language Models: An Analysis of Frontier Developers' Privacy Policies
• A Lightweight Framework for Trigger-Guided LoRA-Based Self-Adaptation in LLMs
• Augmented Structure Preserving Neural Networks for cell biomechanics
• HyFedRAG: A Federated Retrieval-Augmented Generation Framework for Heterogeneous and Privacy-Sensitive Data
• Accelerate Scaling of LLM Alignment via Quantifying the Coverage and Depth of Instruction Set
• MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents
• MORSE: Multi-Objective Reinforcement Learning via Strategy Evolution for Supply Chain Optimization
• Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
• An AI system to help scientists write expert-level empirical software
• Another Turn, Better Output? A Turn-Wise Analysis of Iterative LLM Prompting
• RAFFLES: Reasoning-based Attribution of Faults for LLM Systems
• Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents
• Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference
• AdCare-VLM: Leveraging Large Vision Language Model (LVLM) to Monitor Long-Term Medication Adherence and Care
• LocoMamba: Vision-Driven Locomotion via End-to-End Deep Reinforcement Learning with Mamba
• Livia: An Emotion-Aware AR Companion Powered by Modular AI Agents and Progressive Memory Compression
• Multi-IaC-Eval: Benchmarking Cloud Infrastructure as Code Across Multiple Formats
• Towards Log Analysis with AI Agents: Cowrie Case Study
• Large Language Model Integration with Reinforcement Learning to Augment Decision-Making in Autonomous Cyber Operations
• Evaluation of Large Language Models for Anomaly Detection in Autonomous Vehicles
• Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning
• Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models
• A Dataset Generation Scheme Based on Video2EEG-SPGN-Diffusion for SEED-VD
• Characterizing Fitness Landscape Structures in Prompt Engineering
• Murphys Laws of AI Alignment: Why the Gap Always Wins
• Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs
• Hyperbolic Large Language Models
• DRF: LLM-AGENT Dynamic Reputation Filtering Framework
• Decision-Focused Learning Enhanced by Automated Feature Engineering for Energy Storage Optimisation
• Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL
• From Long to Short: LLMs Excel at Trimming Own Reasoning Chains
• PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments
• Proof2Silicon: Prompt Repair for Verified Code and Hardware Generation via Reinforcement Learning
• REMI: A Novel Causal Schema Memory Architecture for Personalized Lifestyle Recommendation Agents
• SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents
• From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs
• Can AI Make Energy Retrofit Decisions? An Evaluation of Large Language Models
• Large Language Models as Virtual Survey Respondents: Evaluating Sociodemographic Response Generation
• Evaluating Multi-Turn Bargain Skills in LLM-Based Seller Agent
• Teaching AI Stepwise Diagnostic Reasoning with Report-Guided Chain-of-Thought Learning
• Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning
• Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArts
• MVRS: The Multimodal Virtual Reality Stimuli-based Emotion Recognition Dataset
• Benchmarking Large Language Models for Personalized Guidance in AI-Enhanced Learning
• SasAgent: Multi-Agent AI System for Small-Angle Scattering Data Analysis